feat(apple): screen-audio sharing -- macOS ScreenCaptureKit, iOS ReplayKit

Implement system/desktop audio sharing on the Apple clients, feeding the
existing SCREEN_AUDIO Opus -> AEAD -> UDP path via vc_stream_feed_pcm. No
C++/protocol/codec changes -- the core was already ready (the Windows-only
loopback is #ifdef VOICECAT_HAS_LOOPBACK; off Windows the stream just waits
for fed PCM). Audio only; video is dropped.

macOS (in-process):
- ScreenAudioCapture.swift drives an audio-only SCStream
  (excludesCurrentProcessAudio), converts Float32 -> int16 in the channel's
  mono/stereo mode, and calls feedPcm. Capture starts on the self
  .streamStarted event (effective config known then). Wired into
  MainWindowController.screenAudioClicked().

iOS (forward-to-host, single session):
- VoiceCatBroadcast: a ReplayKit Broadcast Upload Extension consumes
  .audioApp only, resamples to 48kHz int16 stereo (AVAudioConverter), and
  writes a shared App Group SPSC ring (BroadcastAudioRing.swift). It does
  not link libvoicecat.
- Host BroadcastAudioPump drains the ring (reacting to the extension's
  Darwin notifications) and feeds the SCREEN_AUDIO stream it owns, downmixing
  to mono when the channel is mono. Screen audio appears as a second stream
  of the same user; no credentials persisted. UI is RPSystemBroadcastPicker
  View in VoiceControlsView. Removes the speculative BroadcastCredentials.

Docs: voice.md s9, CLAUDE.md status, PROGRESS.md.
This commit is contained in:
2026-06-21 00:14:31 +02:00
parent 6ab78fa792
commit 8c90e250f0
17 changed files with 985 additions and 69 deletions

View File

@@ -29,6 +29,8 @@ struct VoiceState {
var level: Float = 0.0
var currentDeviceId: String?
var localStreamId: UInt32 = 0
var screenSharing = false
var screenStreamId: UInt32 = 0
}
// MARK: - SessionState
@@ -49,6 +51,10 @@ final class SessionState {
var accounts: [Account] = []
var devices: [Device] = []
/// Host side of iOS screen-audio sharing drains the broadcast extension's App Group ring
/// and feeds the SCREEN_AUDIO stream this session owns. See BroadcastAudioPump.
private let broadcastPump = BroadcastAudioPump()
init(client: VoiceCatClient, selfUserId: UInt32, permissions: Permissions) {
self.client = client
self.selfUserId = selfUserId
@@ -64,9 +70,13 @@ final class SessionState {
client.onLevel = { [weak self] _, rms in
Task { @MainActor [weak self] in self?.voiceState.level = rms }
}
broadcastPump.onBroadcastStarted = { [weak self] in self?.startScreenShare() }
broadcastPump.onBroadcastFinished = { [weak self] in self?.stopScreenShare() }
broadcastPump.start()
}
deinit {
broadcastPump.stop()
MainActor.assumeIsolated {
AudioSessionManager.shared.client = nil
}
@@ -100,6 +110,19 @@ final class SessionState {
let who = users.first(where: { $0.id == ev.userId })?.nickname ?? "user \(ev.userId)"
addActivity(talking ? "\(who) started talking" : "\(who) stopped talking")
case .streamStarted:
// Our own SCREEN_AUDIO stream is live begin draining the broadcast ring into it,
// in the stream's effective channel mode (downmix to mono if the channel is mono).
if ev.userId == selfUserId && ev.streamId == voiceState.screenStreamId {
let sid = voiceState.screenStreamId
let (r, cfg) = client.getStreamAudioConfig(userId: selfUserId, streamId: sid)
let channels: UInt32 = (r == .ok && cfg?.stereo == true) ? 2 : 1
let c = client
broadcastPump.beginFeeding(streamChannels: channels) { pcm, samples, ch in
c.feedPcm(streamId: sid, pcm: pcm, samplesPerChannel: samples, channels: ch)
}
addActivity("Sharing screen audio (\(channels == 2 ? "stereo" : "mono"))")
break
}
// A remote user started a stream ensure the audio session is active so we can
// hear them even if we haven't joined voice ourselves.
if ev.userId != selfUserId {
@@ -236,6 +259,41 @@ final class SessionState {
// disconnecting from the server (see AppState.disconnect / .disconnected event).
}
// MARK: - Screen audio share
/// Called when the broadcast extension becomes active. Announces the SCREEN_AUDIO stream;
/// feeding begins on the resulting `.streamStarted` event (see handleEvent). The actual
/// system-audio capture happens in the ReplayKit upload extension (a separate process).
private func startScreenShare() {
guard voiceState.screenStreamId == 0 else { return }
guard currentChannelId != 0 else {
addActivity("Screen audio ignored — join a channel first")
return
}
let (result, streamId) = client.startStream(
StreamDescriptor(kind: .screenAudio, deviceId: nil, label: "Screen audio"))
if result == .ok {
voiceState.screenStreamId = streamId
voiceState.screenSharing = true
addActivity("Screen audio share starting…")
} else {
addActivity("Failed to start screen audio: \(result.description)")
}
}
/// Called when the broadcast ends (or on disconnect). Stops feeding and the stream.
private func stopScreenShare() {
broadcastPump.endFeeding()
if voiceState.screenStreamId != 0 {
client.stopStream(voiceState.screenStreamId)
voiceState.screenStreamId = 0
}
if voiceState.screenSharing {
voiceState.screenSharing = false
addActivity("Stopped sharing screen audio")
}
}
func setMute(_ muted: Bool, deafened: Bool) {
client.setSelfMute(micMuted: muted, deafened: deafened)
voiceState.selfMuted = muted